chengbinjin / real-time-style-transfer Goto Github PK
View Code? Open in Web Editor NEWTensorflow implementation of Justin Johnson's paper, perceptual losses for real-time style transfer and super-resolution.
Tensorflow implementation of Justin Johnson's paper, perceptual losses for real-time style transfer and super-resolution.
Thanks for you codes,following your code and style images,I re-train the models ,but the tv loss tends to 0 during training,thus the results become to pure color.Have you ever had such a problem?How to balance various loss weights?thanks
Thanks a lot for ur implementation. I have re-implemented this paper following ur code. But the result was not as ideal as the original paper. Espeicially, the generater images are kinds of speckled. Did u find such phenomenon?
Thank you for the code! I was trying to run this code, but got a traceback.
Traceback (most recent call last):
File "main.py", line 76, in <module>
tf.app.run()
File "C:\Users\Username\Documents\GitHub\Projectname\.venv\lib\site-packages\tensorflow\python\platform\app.py", line 126, in run
_sys.exit(main(argv))
File "main.py", line 71, in main
solver = Solver(FLAGS)
File "C:\Users\Username\Documents\GitHub\Projectname\solver.py", line 37, in __init__
self.model = StyleTranser(self.sess, self.flags, self.num_iters)
File "C:\Users\Username\Documents\GitHub\Projectname\style_transfer.py", line 36, in __init__
self._build_net()
File "C:\Users\Username\Documents\GitHub\Projectname\style_transfer.py", line 48, in _build_net
vgg_dic = self.vgg(self.style_img_ph)
File "C:\Users\Username\Documents\GitHub\Projectname\style_transfer.py", line 219, in __call__
kernels, bias = self.weights[i][0][0][0][0]
ValueError: too many values to unpack (expected 2)
How should I solve this?
I matched all python package requirements to what was written in this repository
The pretrained network link seems to have a broken link. It would be of great help if you could fix that.
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.